Skip to main content
Glama
166,494 tools. Last updated 2026-05-31 22:42

"namespace:io.github.Surendhar-23" matching MCP tools:

  • Recherche de professionnels de santé libéraux conventionnés dans un rayon géographique. Précision géo HYBRIDE depuis le géocodage BAN (Chantier C) : ~77 % des PS sont géolocalisés à l'adresse précise (rue/bâtiment, `distance_km` exacte au m près), ~23 % restent au centroïde commune (~3 km, repli pour adresses non géocodables — DROM, Monaco, CEDEX, lieux-dits). Lire `geo_precision` PAR résultat — ne pas présumer une précision uniforme. Codes type_ps Ameli présents en base (3) : '1' médecins, '2' auxiliaires médicaux (fourre-tout : IDE, kinés, sages-femmes, podologues, orthophonistes, orthoptistes, IPA), '5' chirurgiens-dentistes. Pour cibler une profession précise (ex: IDE seuls, kinés seuls, podologues seuls), passer par `specialite_codes` plutôt que `type_ps_codes` qui ratisse plus large. Liste exhaustive des codes spécialité disponibles via le tool `lister_nomenclature(referentiel:'ameli_specialites')`. Multi-sites : par défaut un PS exerçant sur N adresses apparaît N fois — utiliser `dedupe_by_ps=true` pour regrouper par praticien et lister les sites en sous-objet. Distance retournée en km vol d'oiseau (haversine PostGIS) — pour distance routière, croiser avec un service externe (OSRM, ORS). Chaque PS géolocalisé porte `geo_precision` ∈ {`"adresse"`, `"centroide_commune"`} : `"adresse"` = coords BAN précises, `distance_km` exacte, classement individuel fiable ; `"centroide_commune"` = ~3 km, `distance_km` IDENTIQUE pour tous les PS d'une même commune (non discriminante intra-commune — filtre de zone uniquement, pas de classement/choix d'un PS individuel). **Param `precise_only`** (défaut false) : à true, exclut les PS au centroïde commune et ne renvoie que les ~77 % géocodés à l'adresse BAN (`distance_km` exacte) — recommandé pour les rayons courts (<3 km) et le classement intra-commune. PÉRIMÈTRE : libéraux conventionnés UNIQUEMENT. HORS PÉRIMÈTRE : médecins exclusivement hospitaliers/salariés, biologistes médicaux salariés en LBM, anatomopathologistes hospitaliers, médecins du travail, médecine légale. Pour effectifs tous statuts, voir Annuaire Santé ANS (RPPS, esante.gouv.fr) — non couvert par ce serveur. Source : Annuaire santé Ameli (Assurance Maladie), MAJ hebdomadaire. Réutilisation soumise à l'art. L.1461-2 CSP — citer la source et la date de sync.
    Connector
  • Get everything about a US public company in one call. Use when a user asks "tell me about X", "research Acme", "brief me on Tesla", or you'd otherwise call 10+ pack tools across SEC EDGAR, XBRL, USPTO, news, GLEIF. Returns: cik + company_name; recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC — Run 6 fix landed real FY2025 numbers, not stale FY2022); patents (USPTO PatentsView API was sunset May 2025; pack soft-fails until reactivated); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. Pass ticker "AAPL" or zero-padded CIK "0000320193" — names not supported (use resolve_entity first).
    Connector
  • Fact-check, verify, validate, or confirm/refute a natural-language factual claim or statement against authoritative sources. Use when an agent needs to check whether something a user said is true ("Is it true that…?", "Was X really…?", "Verify the claim that…", "Validate this statement…"). v1 supports company-financial claims (revenue, net income, cash position for public US companies) via SEC EDGAR + XBRL. Returns a verdict (confirmed / approximately_correct / refuted / inconclusive / unsupported), extracted structured form, actual value with pipeworx:// citation, and percent delta. Replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → numeric comparison).
    Connector
  • Découverte des nomenclatures de codes du serveur (tool unique paramétré par `referentiel`) — à appeler avant de filtrer un autre tool plutôt que deviner les codes. ⚠️ Les 3 nomenclatures sont DISTINCTES : un même nombre y désigne des choses différentes (ex '10' = Médecin côté ANS, Neurochirurgien côté Ameli). Ne JAMAIS passer un code d'un référentiel à un paramètre d'un autre — le filtre renverrait vide sans erreur. `referentiel` : - `ameli_specialites` — codes `specialite_code` Ameli (libéraux conventionnés Assurance Maladie / CNAM) : libellé natif, `type_ps_code` de rattachement, count, `libelle_clarifie` (désambigüise les libellés partagés, ex "Médecin généraliste" = 01/22/23 ; "Psychiatre" = 33/75), `is_libelle_partage`. Pour filtrer `professionnels_in_radius` / `professionnels_par_specialite_dept` (param `specialite_code(s)`). - `ameli_types_ps` — codes `type_ps` Ameli : `libelle_source`, `libelle_clarifie` (résout l'ambiguïté du code "2" fourre-tout), count, et `specialites_presentes` (spécialités regroupées). Payload léger via `include_specialites: false` (→ `nb_specialites`). - `rpps_savoir_faire` — spécialités médicales `savoir_faire_code` RPPS / Annuaire Santé ANS (ex 'SM04' Cardiologie). Pour filtrer `densite_sante` (cible professionnels) / `professionnels_rpps_*`. Filtre par `profession_code` (défaut '10' Médecin ; string vide ou 'null' = tous savoir_faire). Paginé : `limit` (défaut 50), réponse expose `total` et `truncated`. PÉRIMÈTRE : libéraux conventionnés UNIQUEMENT. HORS PÉRIMÈTRE : médecins exclusivement hospitaliers/salariés, biologistes médicaux salariés en LBM, anatomopathologistes hospitaliers, médecins du travail, médecine légale. Pour effectifs tous statuts, voir Annuaire Santé ANS (RPPS, esante.gouv.fr) — non couvert par ce serveur. Source : Annuaire santé Ameli (Assurance Maladie), MAJ hebdomadaire. Réutilisation soumise à l'art. L.1461-2 CSP — citer la source et la date de sync.
    Connector
  • Create a new Kochava FAA (Free App Analytics) account. IMPORTANT: The user MUST explicitly agree to the FAA Terms of Service before account creation. If tos_agreed is False, this tool will return the TOS link and stop — do NOT submit the form. Call kochava_free_app_analytics_get_tos() to retrieve and present the TOS to the user first, then call this tool again with tos_agreed=True once the user confirms agreement. DISPLAY INSTRUCTIONS: When this tool returns a successful response, you MUST display the 'next_steps' field content to the user EXACTLY as written — word-for-word, preserving ALL text, formatting, line breaks, numbering, and bullet points. Do NOT summarize, rephrase, reword, or omit any part of the 'next_steps' content. Every sentence must be shown to the user as-is. FAA Terms of Service: https://s34035.pcdn.co/wp-content/uploads/2023/08/FAA-Web-Sign-Up-TOS-8-15-23.pdf Example (after user reviews and agrees to TOS): kochava_free_app_analytics_create_acc_and_get_auth_key( first_name="Jane", last_name="Smith", email_address="jane@example.com", phone_number="5551234567", company="Acme Corp", website="www.acme.com", company_address_line_1="123 Main St", company_city="Sandpoint", company_region="Idaho", company_postal_code="83864", country="United States", tos_agreed=True )
    Connector
  • Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.
    Connector

Matching MCP Servers

Matching MCP Connectors

  • Access live company and contact data from Explorium's AgentSource B2B platform.

  • GitHub MCP — wraps the GitHub public REST API (no auth required for public endpoints)

  • Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors) with ai_visibility_check, ranks by score, surfaces which is most/least recognized. Useful for competitive AI-marketing audits: "does Claude know about us as well as our competitors?". Returns ranked list with score, confidence, signal density per entity.
    Connector
  • Generate official sweepstakes rules via the 14-step wizard. BEFORE CALLING: 1) fetch_sweepstakes to get token, dates, name. 2) get_business + get_profile to pre-fill sponsor fields. 3) fetch_rules to check for existing primary rules — if primary exists, warn user new rules will be SECONDARY. Ask wizard questions in order (steps A-N), one at a time or in small groups. Only ask for data you cannot get from API calls. PRIMARY RULES LINK: If result is_primary=true, give user the URL: https://swpp.me/r/[handler] (handler in lowercase from fetch_sweepstakes). RULES LANGUAGE: Always set rules_language="en". The wizard generates ALL legal text server-side — NEVER compose rules language yourself. AMOE URL: The AMOE URL is NOT the entry page URL — the wizard handles AMOE language automatically based on method_of_entry. AGE GATE: Only activate Age Gate when min_age=2 (21+). NEVER for min_age=1 (18+) or min_age=3 (13+). GEOLOCATION: Use the states parameter for geographic eligibility. NEVER use GeoLocation entry settings for state restrictions — GeoLocation is for GPS/IP boundaries only. # create_rules_wizard ## When to use Generate official sweepstakes rules via the 14-step wizard. BEFORE CALLING: 1) fetch_sweepstakes to get token, dates, name. 2) get_business + get_profile to pre-fill sponsor fields. 3) fetch_rules to check for existing primary rules — if primary exists, warn user new rules will be SECONDARY. Ask wizard questions in order (steps A-N), one at a time or in small groups. Only ask for data you cannot get from API calls. PRIMARY RULES LINK: If result is_primary=true, give user the URL: https://swpp.me/r/[handler] (handler in lowercase from fetch_sweepstakes). RULES LANGUAGE: Always set rules_language="en". The wizard generates ALL legal text server-side — NEVER compose rules language yourself. AMOE URL: The AMOE URL is NOT the entry page URL — the wizard handles AMOE language automatically based on method_of_entry. AGE GATE: Only activate Age Gate when min_age=2 (21+). NEVER for min_age=1 (18+) or min_age=3 (13+). GEOLOCATION: Use the states parameter for geographic eligibility. NEVER use GeoLocation entry settings for state restrictions — GeoLocation is for GPS/IP boundaries only. ## Pre-calls required 1. fetch_sweepstakes if the user gave you a sweepstakes name instead of a token 2. fetch_rules(sweepstakes_token) — if primary rules already exist, WARN that new rules will be SECONDARY (not published) 3. get_business — auto-populate sponsor info (legal name, address) 4. get_entry_settings — confirm AMOE state matches the entry method ## Parameters to validate before calling - sweepstakes_token (string, required) — Sweepstakes token (UUID). Get via fetch_sweepstakes. - arv (number, required) — one of: 1, 2 — Approximate Retail Value threshold. 1 = ARV >= $5,000. 2 = ARV < $5,000. - alcohol_sweeps (number, required) — one of: 1, 2 — Is this an alcohol-related sweepstakes? 1 = Yes, 2 = No. - sweepstakes_name (string, required) — Official promotional name (6-60 characters). - start_date (string, required) — Start date (YYYY-MM-DD). - start_time (string, required) — Start time (e.g. "09:00 AM" or "14:00"). - start_timezone (string, required) — Start timezone (e.g. "US/Eastern", "EST", "CST"). - end_date (string, required) — End date (YYYY-MM-DD). - end_time (string, required) — End time (e.g. "11:59 PM" or "23:59"). - end_timezone (string, required) — End timezone. - prize_description (string, required) — Detailed prize description (max 5000 chars). - prize_include_travel (boolean, required) — Does the prize include travel? - prize_is_vehicle (boolean, required) — Is the prize a vehicle? - prize_value (number, required) — Total prize value in USD. Must be > 0. - entry_period_selector (number, required) — one of: 1, 2 — 1 = single drawing period, 2 = multiple entry periods. - sponsor_name (string, required) — Legal sponsor name. Pre-fill from get_business. - sponsor_address (string, required) — Sponsor street address. Pre-fill from get_business. - sponsor_city (string, required) — Sponsor city. Pre-fill from get_business. - sponsor_state (string, required) — Sponsor state or abbreviation. Pre-fill from get_business. - sponsor_zip_code (string, required) — Sponsor zip code (5 digits). Pre-fill from get_business. - method_of_entry (number, required) — one of: 1, 2, 3, 4, 5, 6, 7, 8 — Entry method: 1=Website, 2=SMS, 3=Social Media, 4=Other, 5=Purchase ($1=1 entry), 6=Purchase (1 order=1 entry), 7=Donation, 8=Subscription. - min_age (number, required) — one of: 1, 2, 3 — Minimum age: 1=18+, 2=21+, 3=13+ with parental consent. - states (number, required) — one of: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 — Geographic eligibility. 1=All 50+DC, 2=+PR, 3=+All Territories, 4=Select specific, 5=US&Canada, 6=US&Canada+PR, 7=US&UK, 8=US&Mexico, 9=Worldwide, 10=US,Canada,Mexico. - privacy_policy_url (string, required) — Privacy policy URL (min 11 chars, must include http/https). - sweeppea_entry_page (number, required) — one of: 1, 2, 3 — 1 = Sweeppea hosted page, 2 = custom URL, 3 = none. - winners_to_draw (number, optional) — Number of winners to draw (>= 1). Required when entry_period_selector = 1. - winner_drawing_date (string, optional) — Drawing date (YYYY-MM-DD). Required when entry_period_selector = 1. - winner_drawing_time (string, optional) — Drawing time. Required when entry_period_selector = 1. - winner_drawing_timezone (string, optional) — Drawing timezone. Required when entry_period_selector = 1. - winner_notification_date (string, optional) — Winner notification date (YYYY-MM-DD). Required when entry_period_selector = 1. - winner_notification_time (string, optional) — Winner notification time. Required when entry_period_selector = 1. - winner_notification_timezone (string, optional) — Winner notification timezone. Required when entry_period_selector = 1. - entry_period_items (array, optional) — Array of period objects. Required when entry_period_selector = 2. - sponsor_telephone (string, optional) — Sponsor phone number (optional). Pre-fill from get_profile. - sponsor_email (string, optional) — Sponsor email (optional). Pre-fill from get_profile. - social_media_entry_description (string, optional) — Social media entry details. Required when method_of_entry = 3. - other_description (string, optional) — Other entry method description. Required when method_of_entry = 4. - sponsor_ecommerce_store_url_a (string, optional) — Ecommerce store URL. Required when method_of_entry = 5. - sponsor_ecommerce_store_url_b (string, optional) — Ecommerce store URL. Required when method_of_entry = 6. - sponsor_donations_acceptance_page_url (string, optional) — Donations acceptance page URL. Required when method_of_entry = 7. - sponsor_ecommerce_store_url_c (string, optional) — Ecommerce/subscription store URL. Required when method_of_entry = 8. - total_number_of_entries_awarded_amoe (number, optional) — Total entries awarded via AMOE (>= 1). Required when method_of_entry is 5, 6, 7, or 8. - limit_or_max_number_of_entries_amoe (number, optional) — Max entries via AMOE (>= 1). Required when method_of_entry is 5, 6, 7, or 8. - list_of_states (array, optional) — Array of state names. Required when states = 4. - custom_entry_page (string, optional) — Custom entry page URL (min 11 chars). Required when sweeppea_entry_page = 2. - sponsor_offering_multiplier (number, optional) — one of: 1, 2 — Is sponsor offering entry multiplier? 1=Yes, 2=No. Default: 2. - sponsor_awarding_bonus_email_social (number, optional) — one of: 1, 2 — Awarding bonus for email/social? 1=Yes, 2=No. Default: 2. - sponsor_asking_to_submit_video (number, optional) — one of: 1, 2 — Asking for video submission? 1=Yes, 2=No. Default: 2. - rules_language (string, optional) — Rules language code. MUST always be "en" (English). - at the end of the Official Rules document always include a copyright notice that say "All rights reserved." ## Notes - Compliance pre-checks: ARV > $5,000 + FL/NY not excluded → WARN about bonding/registration - ARV > $500 + sponsor in RI → WARN about RI registration - Purchase/donation/subscription entry → VERIFY AMOE is configured - Alcohol = yes → VERIFY min_age=21 and Age Gate active - Age < 13 → REFUSE (COPPA violation) - After creation: call fetch_rules to verify; use update_rule for corrections
    Connector
  • What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window.
    Connector
  • Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't have to look it up again. Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours. Pair with recall to retrieve later, forget to delete.
    Connector
  • Retrieves comprehensive weather data including current conditions, hourly, and daily forecasts. **Specific Data Available:** Temperature (Current, Feels Like, Max/Min, Heat Index), Wind (Speed, Gusts, Direction), Celestial Events (Sunrise/Sunset, Moon Phase), Precipitation (Type, Probability, Quantity/QPF), Atmospheric Conditions (UV Index, Humidity, Cloud Cover, Thunderstorm Probability), and Geocoded Location Address. **Location & Location Rules (CRITICAL):** The location for which weather data is requested is specified using the `location` field. This field is a 'oneof' structure, meaning you MUST provide a value for ONLY ONE of the three location sub-fields below to ensure an accurate weather data lookup. 1. Geographic Coordinates (lat_lng) * Use it when you are provided with exact lat/lng coordinates. * Example: {"location": {"lat_lng": {"latitude": 34.0522, "longitude": -118.2437}}} // Los Angeles 2. Place ID (place_id) * An unambiguous string identifier (Google Maps Place ID). * The place_id can be fetched from the search_places tool. * Example: {"location": {"place_id": "ChIJLU7jZClu5kcR4PcOOO6p3I0"}} // Eiffel Tower 3. Address String (address) * A free-form string that requires specificity for geocoding. * City & Region: Always include region/country (e.g., "London, UK", not "London"). * Street Address: Provide the full address (e.g., "1600 Pennsylvania Ave NW, Washington, DC"). * Postal/Zip Codes: MUST be accompanied by a country name (e.g., "90210, USA", NOT "90210"). * Example: {"location": {"address": "1600 Pennsylvania Ave NW, Washington, DC"}} **Usage Modes:** * **Current Weather:** Provide `location` only. Do not specify `date` and `hour`. * **Hourly Forecast:** Provide `location`, `date`, and `hour` (0-23). Use for specific times (e.g., "at 5 PM") or terms like "next few hours" or "later today". If the user specifies minute, round down to the nearest hour. Hourly forecast beyond 120 hours from now is not supported. Historical hourly weather is supported up to 24 hours in the past. * **Daily Forecast:** Provide `location` and `date`. Do not specify `hour`. Use for general day requests (e.g., "weather for tomorrow", "weather on Friday", "weather on 12/25"). If today's date is not in the context, you should clarify it with the user. Daily forecast beyond 10 days including today is not supported. Historical weather is not supported. **Parameter Constraints:** * **Timezones:** All `date` and `hour` inputs must be relative to the **location's local time zone**, not the user's time zone. * **Date Format:** Inputs must be separated into `{year, month, day}` integers. * **Units:** Defaults to `METRIC`. Set `units_system` to `IMPERIAL` for Fahrenheit/Miles if the user implies US standards or explicitly requests it. * The grounded output must be attributed to the source using the information from the `attribution` field when available.
    Connector
  • Retrieves comprehensive weather data including current conditions, hourly, and daily forecasts. **Specific Data Available:** Temperature (Current, Feels Like, Max/Min, Heat Index), Wind (Speed, Gusts, Direction), Celestial Events (Sunrise/Sunset, Moon Phase), Precipitation (Type, Probability, Quantity/QPF), Atmospheric Conditions (UV Index, Humidity, Cloud Cover, Thunderstorm Probability), and Geocoded Location Address. **Location & Location Rules (CRITICAL):** The location for which weather data is requested is specified using the `location` field. This field is a 'oneof' structure, meaning you MUST provide a value for ONLY ONE of the three location sub-fields below to ensure an accurate weather data lookup. 1. Geographic Coordinates (lat_lng) * Use it when you are provided with exact lat/lng coordinates. * Example: {"location": {"lat_lng": {"latitude": 34.0522, "longitude": -118.2437}}} // Los Angeles 2. Place ID (place_id) * An unambiguous string identifier (Google Maps Place ID). * The place_id can be fetched from the search_places tool. * Example: {"location": {"place_id": "ChIJLU7jZClu5kcR4PcOOO6p3I0"}} // Eiffel Tower 3. Address String (address) * A free-form string that requires specificity for geocoding. * City & Region: Always include region/country (e.g., "London, UK", not "London"). * Street Address: Provide the full address (e.g., "1600 Pennsylvania Ave NW, Washington, DC"). * Postal/Zip Codes: MUST be accompanied by a country name (e.g., "90210, USA", NOT "90210"). * Example: {"location": {"address": "1600 Pennsylvania Ave NW, Washington, DC"}} **Usage Modes:** * **Current Weather:** Provide `location` only. Do not specify `date` and `hour`. * **Hourly Forecast:** Provide `location`, `date`, and `hour` (0-23). Use for specific times (e.g., "at 5 PM") or terms like "next few hours" or "later today". If the user specifies minute, round down to the nearest hour. Hourly forecast beyond 120 hours from now is not supported. Historical hourly weather is supported up to 24 hours in the past. * **Daily Forecast:** Provide `location` and `date`. Do not specify `hour`. Use for general day requests (e.g., "weather for tomorrow", "weather on Friday", "weather on 12/25"). If today's date is not in the context, you should clarify it with the user. Daily forecast beyond 10 days including today is not supported. Historical weather is not supported. **Parameter Constraints:** * **Timezones:** All `date` and `hour` inputs must be relative to the **location's local time zone**, not the user's time zone. * **Date Format:** Inputs must be separated into `{year, month, day}` integers. * **Units:** Defaults to `METRIC`. Set `units_system` to `IMPERIAL` for Fahrenheit/Miles if the user implies US standards or explicitly requests it. * The grounded output must be attributed to the source using the information from the `attribution` field when available.
    Connector
  • Computes physical (23-day), emotional (28-day), and intellectual (33-day) biorhythm cycles for a birth date. SECTION: WHAT THIS TOOL COVERS Returns cycle values (-1.0 to +1.0), percentage, phase label (High/Rising/Falling/Low), and critical day flags for each cycle. Critical days occur when a cycle crosses the zero line — these represent instability and vulnerability to poor judgment or accidents. Supports single-day snapshot (days=1) and multi-day range (up to 90 days). Formula: sin(2π × t / cycle_length) where t = days since birth. Also returns composite_score (average of three cycles) and has_critical_day flag. Biorhythm is a Western concept — Vedic equivalents are Tarabala and Chandrabala (use asterwise_get_nakshatra_prediction for the Vedic equivalent). SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_nakshatra_prediction — for the Vedic personalized daily prediction. SECTION: INPUT CONTRACT birth_date (required): Date of birth in YYYY-MM-DD format. target_date (optional): Date to compute for. Defaults to today. days (optional int 1-90): Number of consecutive days. Default 1. SECTION: OUTPUT CONTRACT (single day) data.birth_date, data.target_date, data.days_since_birth (int) data.cycles{}: physical, emotional, intellectual — each: value (float -1.0 to +1.0), percentage (float), phase (string), is_critical (bool), cycle_length_days (int), description (string) data.critical_today[] (string array of cycle names that are critical) data.has_critical_day (bool) data.composite_score (float — average of three cycles) data.note (string — explains Vedic equivalents) SECTION: OUTPUT CONTRACT (date range, days > 1) data.birth_date, data.start_date, data.end_date, data.days data.daily[] — array of day objects each with date, cycles{}, critical[], composite_score SECTION: COMPUTE CLASS FAST_LOOKUP — pure math, no ephemeris. SECTION: ERROR CONTRACT INVALID_PARAMS (upstream): birth_date after target_date → INTERNAL_ERROR INTERNAL_ERROR: Any upstream API failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_nakshatra_prediction — Vedic Tarabala/Chandrabala daily prediction. asterwise_get_panchanga — Vedic daily panchanga elements, not biorhythm cycles.
    Connector
  • Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred + kalshi_macro + federal_register; Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires; result.evidence is keyed by source. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets return status:"market_closed_or_inactive" and skip fan-out. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note.
    Connector
  • Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. TWO MODES: (1) `event` — pass a single Polymarket event slug; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). (2) `topic` — pass a seed question ("Strait of Hormuz traffic returns to normal"); searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response carries opportunities[] (gap_pp, suggested_trade, reasoning) plus partition_check when in event mode (with placeholders_filtered count).
    Connector
  • Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped into three response segments under by_segment: (1) MODEL_DRIVEN — crypto_price (lognormal barrier from 90d FRED log-returns) and news_momentum (GDELT 7d/21d article-volume ratio, soft signal w/ halved Kelly). (2) STRUCTURAL_ARBITRAGE — partition_overround on mutually-exclusive events; per-leg favorite-longshot bias correction with per-sport α (tennis 1.02, soccer 1.10, MMA 1.15, default 1.0); placeholder-slug filter drops will-person-X / will-team-Y / will-manager-Z / will-someone-else- backstops; partitions with >20% placeholder fraction skipped entirely. (3) CONCENTRATED_LONGSHOT — basket trade when one leg ≥85% AND ≥2 longshots ≤5% AND portfolio return ≥50:1; rare-by-design. EVERY OPPORTUNITY carries edge_pp_net (after slippage), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume. TRADEABLE-EDGE KNOBS: min_liquidity / max_spread_pp drop opportunities where edge isn't realizable; min_partition_leg_kelly filters partitions by best per-leg Kelly. Cached 1h at the KV level keyed on all knobs. fed_rate bets are scanned but EXCLUDED from ranking (1m-T vs EFFR signal is unreliable at meeting-month horizons without paid OIS/SOFR-futures data); see fed_rate_context for raw spread.
    Connector
  • Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scratch. Scoped to your identifier (anonymous IP, BYO key hash, or account ID). Pair with remember to save, forget to delete.
    Connector
  • Cross-venue spread between Kalshi and Polymarket for the same resolving question. Kalshi and Polymarket frequently price the same event 2-25pp apart because the venues have different participant pools — that delta is a real arb signal. TWO MODES: (1) `topic` — pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope") that auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings. Returns: each venue's leg-by-leg prices (in raw probability, 0-1), and where a leg from each side maps to the same outcome, the spread (Kalshi − Polymarket) in percentage points.
    Connector
  • Display a holiday photo to the user by creating an HTML artifact that embeds the photo from its hosted URL. After calling this tool you MUST create an HTML artifact (type text/html) whose body is a single <img> tag pointing at the hosted URL returned in the result. Do not write a prose description, caption, or commentary — the user wants to view the photo, not read about it. Use list_photos first to discover valid IDs.
    Connector
  • Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.
    Connector